KanBots — A kanban that runs parallel agents on every card
- title
- KanBots — A kanban that runs parallel agents on every card
- author
- KanBots
- fetched
- 2026-07-21
KanBots
A kanban that runs parallel agents on every card.
Drop a folder. Get a board. Dispatch any of 11 agent CLIs — Claude Code, Codex, Gemini, Cursor, Copilot, Amp, and more — on as many cards as you want, each in its own worktree. Or hit autopilot and let personas split the work, run in parallel, and check their own output while you sleep.
Free forever · MIT licensed
Stats highlighted on the page:
- 11 agent CLIs supported: Claude · Codex · Gemini · Cursor · Copilot · Amp · +5
- 0 bytes leave your machine
- MIT license · free forever
State stored in .kanbots/db.sqlite · local-first · 0 telemetry.
Solo on a laptop, or a team that ships together.
Same kanban metaphor. Same agent runtime. Different scale of collaboration. Both are legitimate paths.
KanBots OSS (FREE FOREVER, MIT)
Desktop · local-first · no account · no telemetry. $0 + pay-what-you-can donations. macOS · Linux · Windows · all features included.
- Parallel agent dispatch
- Autopilot — feature-dev + qa
- Decision prompts
- Personas (built-in + custom)
- Cost analytics, live
- Recipe library
- MCP server (kanbots-mcp-server)
- Sentry import
- GitHub Issues mode (personal PAT)
- Branch preview
- Promote / draft PR
- 11 agent CLIs (Claude Code, Codex, Gemini, Cursor, Copilot, +6)
- Pre-push hook (containment)
KanBots Cloud (FOR TEAMS, per-seat)
Hosted · multi-user · agents stay local on your hardware. $19 per seat / month · $190 billed yearly. Everything in OSS, plus:
- Real-time presence on the board
- Assignment notifications to teammates
- Cross-device sync
- Audit log for compliance (Enterprise)
- SSO / SCIM (Enterprise)
- Slack notifications
- Org-wide cost rollup
- Real-time collaborative card editing
- Per-org agent activity dashboard
- REST API + PATs (Enterprise)
- Outbound webhooks (Enterprise)
- Managed GitHub App
Positioning note: "Every Cloud-only feature requires either another person or another device in the picture. None of them help a solo user on one machine — so we don't gate them. OSS is what one person does on their machine; Cloud is what a team does together."
Integrations
Claude Code (CLI), Codex (CLI), Gemini (CLI), Cursor (CLI · MCP), Copilot (CLI), Amp + 5 more (CLI), GitHub (Issues + PRs), Sentry (Error import).
Built for the way agents actually ship (eight features)
Parallel agents on the board — Dispatch on as many cards as you want; each agent runs in its own git worktree on a kanbots/issue-N branch. The board updates live as runs progress, decisions surface, costs accrue.
Autopilot — self-evolving feature dev — Plug in personas (product, engineer, reviewer, tester) and a parallelism count up to 4. The orchestrator round-robins through personas, splits parent issues into subtasks, and evolves the backlog as agents discover work. Personas spawn personas.
Decision prompts you actually answer — Agents pause and ask; you click an option and the run continues. Numbered shortcuts, edit-and-resubmit, slash commands like /spec, /review, /split. Reviewable decisions, not silent tree mutations.
Bring your own CLI — 11 supported agent CLIs: Claude Code, Codex, Gemini, Cursor, Copilot, Amp, OpenCode, Droid, CCR, Qwen, plus any ACP-compatible CLI. Same board, same worktrees, same decision UI behind a single AgentCliAdapter. Reuse the auth you already have.
Local-first, zero servers — Everything lives in .kanbots/ next to your repo: SQLite database, configs, worktrees. No cloud account, no telemetry, no HTTP server. Your code never leaves the machine.
Cost analytics, live — Per-run, per-card, per-project rollups. Watch the cost meter accrue as agents work. Set per-run and per-session caps; runs stop on cost-budget.
GitHub mode + draft PRs — Drive real GitHub issues with your personal PAT. Promote a worktree to a commit, or open a draft PR with one click. A pre-push hook means agents never publish on their own.
MCP server included — kanbots-mcp-server exposes the board over the Model Context Protocol so Cursor, Claude Desktop, or anything MCP-aware can drive it. The board becomes a first-class tool for your other agents.
UI surfaces
Autopilot — Up to 4 parallel slots round-robin through your roster. Each slot atomically claims the next persona; agents split parents into subtasks. Stops on completion or session budget. Built-in personas: Product Manager, Senior Engineer, UX Designer, Growth Lead, Reliability Engineer, Agent Expert (custom).
Decisions — Live thread streams every tool_use and tool_result. When the agent needs a call, the run pauses with numbered options. Reply box accepts slash commands /spec, /review, /split.
Personas — A persona is a named system-prompt snippet. Built-ins ship with the app; "New persona" lets you write your own — save, reuse forever. Custom personas stay on your machine.
Providers — 11 agent CLIs behind one AgentCliAdapter. Per-provider default models (e.g., Claude Opus 4.7, GPT-5, Gemini 2.5 Pro). Switch per dispatch.
Tasks — Templates: Bug fix · Feature · Refactor · Review · Spike. Three start modes: spec-first (run /spec, await approval), create-and-dispatch, or queue-for-later. Title becomes branch + PR title. Branch created off main in .kanbots/worktrees/issue-N.
Chat — General-purpose agent that knows your repo, tests, and git state. Ask questions like "which API routes don't have rate limiting?".
Autopilot detail
Hand kanbots an issue and a budget. The orchestrator round-robins through a roster of personas, runs up to four slots in parallel, splits parent issues into subtasks, and keeps cycling until the work converges or the cost cap hits.
- Pick a roster (built-in or custom personas)
- Set parallelism (1–4) — each slot atomically claims the next persona via a round-robin counter
- Personas split work — agents file new cards on the board; later cycles pick those up
- Stop on budget or completion — per-session cost budget caps total spend; Stop button kills the parent and all children
QA loop: run typecheck / tests / lint / build / e2e in the worktree; optionally start your dev server and watch it. For every failing check, dispatch a fix run on a derived child issue. Repeat until green.
Download
OSS desktop app: macOS .dmg · Windows .exe · Linux .AppImage / .tar.xz. Free · MIT · No account.